© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 12648
    Prev
    Next
    INDEX
    Explanations

    references to movies or film productions

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and formatting elements in movie titles and descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bilt
    -0.75
    ertodd
    -0.70
    Council
    -0.68
    rawdownloadcloneembedreportprint
    -0.68
    ollah
    -0.66
    Statistics
    -0.64
    wcs
    -0.64
    nces
    -0.64
    >>>>>>>>
    -0.64
    otor
    -0.64
    POSITIVE LOGITS
     starring
    1.45
     featuring
    1.06
     narrated
    1.05
     wherein
    1.04
     directed
    1.04
     which
    0.99
     premiered
    0.97
     titled
    0.96
     released
    0.94
    feat
    0.93
    Activations Density 0.183%

    No Known Activations